专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

JP2012198277A Document reading-aloud support device, document reading-aloud support method, and document reading-aloud support program 审中-公开
标题翻译：文档阅读支持设备，文档阅读支持方法和文档阅读支持程序
公开(公告)号：JP2012198277A
公开(公告)日：2012-10-18
申请号：JP2011060702
申请日：2011-03-18
申请人： Toshiba Corp , 株式会社東芝
发明人： NUNOME MITSUO , SUZUKI MASARU , MORITA SHINKO , TACHIBANA KENTARO , MORI KOICHIRO , SHIMIZU YUUJI , KAGOSHIMA TAKEHIKO , TAMURA MASANORI , YAMAZAKI TOSHIHIRO
IPC分类号： G10L13/08 , G10L13/00
CPC分类号： G10L13/10 , G10L13/08 , G10L25/63
摘要： PROBLEM TO BE SOLVED: To provide a document reading-aloud support device for estimating a speech production style by using information extracted from plural sentences.SOLUTION: A document reading-aloud support device includes: model storage means for storing a model that has learned correlation between identity information on plural sentences extracted from a learning-use document and a speech production style; document acquisition means for acquiring a document to be a reading-aloud object; identity information extraction means for extracting identity information from each sentence of the document acquired by the document acquisition means; and speech production style estimation means for collating the identity information on plural sentences extracted by the identity information extraction means with a model stored in the model storage means to estimate the speech production style of each sentence.
摘要翻译：要解决的问题：提供一种用于通过使用从多个句子提取的信息来估计语音产生风格的文档朗读支持设备。文件朗读支持装置包括：模型存储装置，用于存储已经学习了从学习用文档提取的多个句子的身份信息与语音制作风格之间的相关性的模型; 文档获取装置，用于获取要读取的对象的文档; 身份信息提取装置，用于从文档获取装置获取的文档的每个句子提取身份信息; 以及用于将由身份信息提取装置提取的多个句子的身份信息与存储在模型存储装置中的模型对照的语音制作风格估计装置，以估计每个句子的语音制作风格。版权所有（C）2013，JPO＆INPIT

2. 发明专利

JP2009199552A Search navigation device and method 审中-公开
标题翻译：搜索导航设备和方法
公开(公告)号：JP2009199552A
公开(公告)日：2009-09-03
申请号：JP2008043434
申请日：2008-02-25
申请人： Toshiba Corp , 株式会社東芝
发明人： SASAKI HIROSHI , KAWAMURA TAKAHIRO , YAMAZAKI TOSHIHIRO
IPC分类号： G06F17/30
摘要： PROBLEM TO BE SOLVED: To easily specify information that follows a search intention of a user even if a worker does not perform classification work of information beforehand.
SOLUTION: A search navigation server includes: an input receiving part for receiving an input of a search query for searching document data; a searching part for searching document data with a search query; a clustering part for classifying the searched document data to generate a cluster; a label generating part for generating a cluster label for each cluster; a screen information generating part for generating, for each cluster, screen information in which the cluster label and the document data are described; a selection receiving part for receiving selection of the cluster label shown in the screen information, and a merging part for merging a plurality of clusters indicated by a plurality of cluster labels into one cluster when the selection of the plurality of cluster labels is received. The clustering part classifies merged clusters to generate clusters each time the clusters are merged.
COPYRIGHT: (C)2009,JPO&INPIT
摘要翻译：要解决的问题：即使工作人员没有事先进行信息的分类工作，也容易地指定跟随用户的搜索意图的信息。解决方案：搜索导航服务器包括：输入接收部分，用于接收用于搜索文档数据的搜索查询的输入; 用于利用搜索查询来搜索文档数据的搜索部分; 聚类部分，用于对所搜索的文档数据进行分类以生成聚类; 标签生成部，其针对每个群集生成群集标签; 画面信息生成部，其针对每个群集生成描述所述群集标签和文档数据的画面信息; 选择接收部分，用于接收屏幕信息中所示的集群标签的选择;以及合并部分，用于当接收到多个集群标签的选择时，将由多个集群标签指示的多个集群合并成一个集群。聚类部分对合并的集群进行分类，以便在每次集群合并时生成集群。版权所有（C）2009，JPO＆INPIT

3. 发明专利

JP2007272465A Schedule management device, document presentation method for schedule management device, and schedule management program 审中-公开
标题翻译：附表管理装置，附表管理装置的文件陈述方法及附表管理方案
公开(公告)号：JP2007272465A
公开(公告)日：2007-10-18
申请号：JP2006095944
申请日：2006-03-30
申请人： Toshiba Corp , 株式会社東芝
发明人： OKAMOTO YUZO , UMEKI HIDEO , CHO KENTA , TSUBOI SOUGO , YAMAZAKI TOSHIHIRO
IPC分类号： G06F17/30 , G06Q10/00 , G06Q10/06 , G06Q10/10 , G06Q50/00
摘要： PROBLEM TO BE SOLVED: To present an appropriate candidate of a document needed by a user for a selected schedule. SOLUTION: The schedule management device linked with a document storage part storing documents comprises a schedule storage part storing a plurality of schedules each having a time of day; an access history storage part storing access histories from a user to the plurality of documents; a schedule selection part selecting any one of the plurality of schedules displayed on a schedule display part; a similar schedule extraction part extracting a similar schedule similar to the selected schedule from the schedule storage part; a document extraction part retrieving an access history corresponding to the time of day of the similar schedule from the access history storage part and extracting a document corresponding to the access history from the document storage part; and a document candidate presentation part presenting the extracted document as a necessary document candidate. COPYRIGHT: (C)2008,JPO&INPIT
摘要翻译：要解决的问题：呈现用户所选择的时间表所需的文档的适当候选。解决方案：与存储文档的文档存储部分链接的日程管理装置包括存储多个时间表的日程表存储部分，每个日程表具有时间; 访问历史存储部分，存储从用户到多个文档的访问历史; 选择显示在时间表显示部上的多个日程表中的任何一个的日程选择部分; 类似的时间表提取部分从时间表存储部分提取与所选择的时间表相似的类似时间表; 文档提取部分从访问历史存储部分检索与类似日程的时间相对应的访问历史，并从文档存储部分提取与访问历史相对应的文档; 以及呈现提取的文档作为必要的文档候选的文档候选呈现部分。版权所有（C）2008，JPO＆INPIT

4. 发明专利

JP2007264789A Scene information extraction method, scene extraction method and extraction device 有权
标题翻译：场景信息提取方法，场景提取方法和提取装置
公开(公告)号：JP2007264789A
公开(公告)日：2007-10-11
申请号：JP2006086035
申请日：2006-03-27
申请人： Toshiba Corp , 株式会社東芝
发明人： YAMAZAKI TOSHIHIRO , TSUTSUI HIDEKI , TSUBOI SOUGO , TSUCHIYA CHIKAO
IPC分类号： G06F17/30
CPC分类号： H04H60/37 , H04H60/58
摘要： PROBLEM TO BE SOLVED: To accurately extract scene information and a scene.
SOLUTION: This scene information extraction device includes a comment acquisition means 102 for acquiring a plurality of comment information including comment and the start time and end time of the comment in association with content with scenes time-sequentially defined; a division means 103 for performing the morphological analysis of every comment, and for dividing the comment into a plurality of words; a word evaluation value calculating means 105 for calculating the evaluation value of each word showing significance in the extracting the scene for every word; a means 107 for acquiring evaluation value distribution for every word by adding the evaluation values of words corresponding to words for all the divided words since the start time of the comment including each word until the end time of the comment; and an extraction means 108 for extracting the start time and end time of the scene to be extracted from the content based on the shape of the evaluation value distribution.
COPYRIGHT: (C)2008,JPO&INPIT
摘要翻译：要解决的问题：准确提取场景信息和场景。解决方案：该场景信息提取装置包括：注释获取装置102，用于获取包括评论的多个注释信息以及与时间顺序定义的场景相关联的注释的开始时间和结束时间; 分割装置103，用于对每个评论进行形态分析，并将注释分成多个单词; 字评估值计算装置105，用于计算在每个单词提取场景中显示有意义的每个单词的评估值; 用于通过将包括每个单词的评论的开始时间之后的所有分割单词的单词相对应的单词的评估值相加来获得每个单词的评估值分布的单元107，直到该评论结束时为止; 以及提取装置108，用于根据评估值分布的形状从内容中提取要提取的场景的开始时间和结束时间。版权所有（C）2008，JPO＆INPIT

5. 发明专利

JP2009239729A Device, method and program for informing content scene appearance 有权
标题翻译：用于通知内容场景外观的设备，方法和程序
公开(公告)号：JP2009239729A
公开(公告)日：2009-10-15
申请号：JP2008084604
申请日：2008-03-27
申请人： Toshiba Corp , 株式会社東芝
发明人： YAMAZAKI TOSHIHIRO , KAWAMURA TAKAHIRO
IPC分类号： H04N5/445 , H04N7/173
CPC分类号： H04N5/147 , H04N5/44508 , H04N21/44008 , H04N21/478 , H04N21/8405 , H04N21/8545
摘要： PROBLEM TO BE SOLVED: To provide a scene informing device that detects and reports a scene appearance with a high degree of accuracy.
SOLUTION: The scene informing device includes: a metadata extraction portion 120 for extracting the metadata from reproduced scenes; a keyword extraction portion 102 for extracting keywords from the metadata; an applying portion 103 for applying a semantic class to the keywords; and a monitored information acquisition portion 105 for acquiring at least one monitoring keyword other than the keywords to which a reproduction schedule class is applied if the keywords to which the reproduction schedule class for indicating what is reproduced in subsequent scenes is applied are included in the extracted keywords. Further, the device includes: an appearance determining portion 108 for determining that the scene including the monitored keywords has appeared if the monitored keywords and the keywords to which a reproduced class for indicating that the reproduction has been carried out is applied are included in the metadata extracted from the reproduced scenes; and an informing portion 109 for reporting that the scenes including the monitored keywords have appeared.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：提供以高精度检测和报告场景外观的场景通知装置。场景通知装置包括：元数据提取部分120，用于从再现的场景中提取元数据; 用于从元数据中提取关键词的关键词提取部分102; 用于将关键字应用语义类的应用部分103; 以及监视信息获取部分105，用于如果应用了用于指示在后续场景中再现的再现日程表类别的关键词，则获取至少一个监视关键字，除了应用了再现日程表类别的关键词之外，还包括提取的关键词此外，该设备包括：外部确定部分108，其用于确定包括被监视的关键字的场景是否已经出现，如果所监视的关键字和应用了用于指示再现的再现类的关键字被包括在元数据中从再现的场景中提取; 以及用于报告包括所监视的关键字的场景已经出现的通知部分109。版权所有（C）2010，JPO＆INPIT

6. 发明专利

JP2008242838A Description expression adding apparatus, program and description expression adding method 有权
标题翻译：描述表达式的增加装置，程序和说明表达式的添加方法
公开(公告)号：JP2008242838A
公开(公告)日：2008-10-09
申请号：JP2007082620
申请日：2007-03-27
申请人： Toshiba Corp , 株式会社東芝
发明人： YAMAZAKI TOSHIHIRO , TSUTSUI HIDEKI , URATA KOJI
IPC分类号： G06F17/30 , G06F13/00 , H04N7/173 , H04N21/435 , H04N21/83 , H04N21/854
CPC分类号： G11B27/11 , G06F17/30796 , G06F17/30817
摘要： PROBLEM TO BE SOLVED: To activate communication through a video content. SOLUTION: When a scene aggregate including a plurality of scenes, for example, an aggregate of scenes book-marked during the viewing of the video content is inputted, a combination in a meta information aggregate showing characteristics of scenes corresponding to the respective scenes of the input scene aggregate is selected as a description expression as description for discriminating the respective scenes, the combination giving maximum distances between the respective meta information, and the description expression selected for each scene included in the scene aggregate is added to each scene. Thus, it is possible to add a description expression 70 for discriminating the respective scenes to each scene 60, and to facilitate the writing of comments or opinions with respect to a scene 60 book-marked during viewing, and to synchronize the written text and the video content for making them easy to be read, and to activate communication through the video content. COPYRIGHT: (C)2009,JPO&INPIT
摘要翻译：要解决的问题：通过视频内容激活通信。解决方案：当输入包括多个场景的场景聚合，例如，在视频内容的观看期间被书签的场景的聚合时，表示与相应的视频对应的场景的特征的元信息聚合中的组合选择输入场景聚合的场景作为描述用于识别各个场景的描述表达，给各个元信息之间给出最大距离的组合和为场景聚合中包括的每个场景选择的描述表达式被添加到每个场景。因此，可以添加用于将各个场景区分为每个场景60的描述表达70，并且便于关于在观看期间书签的场景60的意见或意见的写入，并且使书面文本和视频内容，使其易于阅读，并通过视频内容激活通信。版权所有（C）2009，JPO＆INPIT

7. 发明专利

JP2006155368A Schedule management device, schedule management method and program 有权
标题翻译：时间表管理装置，时间表管理方法和程序
公开(公告)号：JP2006155368A
公开(公告)日：2006-06-15
申请号：JP2004347105
申请日：2004-11-30
申请人： Toshiba Corp , 株式会社東芝
发明人： CHO KENTA , HATTORI MASANORI , OKAMOTO YUZO , OKAMOTO MASAYUKI , YAMAZAKI TOSHIHIRO
IPC分类号： G06Q10/00 , G06Q10/06 , G06Q10/10 , G06Q50/00
CPC分类号： G06Q10/06 , G06Q10/06311 , G06Q10/1097
摘要： PROBLEM TO BE SOLVED: To provide a schedule management device, a schedule management method and a program for efficiently operating the schedule management of a task. SOLUTION: A context is estimated by applying a context estimation rule to the spare time on schedule of a user. A task inputted by a task input means is divided into a plurality of sub-tasks based on a task template. A task recommendation rule for recommending the task to be executed is applied to the emulated spare time of the user from the relation of the context and the meta data of the task and the task to be executed in the spare time is recommended based on the context of the spare time and the meta data of the sub-tasks. The recommended task is managed as a schedule. COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：提供一种时间表管理装置，时间表管理方法和用于有效地操作任务的进度管理的程序。解决方案：通过将上下文估计规则应用于用户的业务时间来估计上下文。由任务输入装置输入的任务根据任务模板分为多个子任务。推荐执行任务的任务推荐规则从上下文与任务的元数据的关系应用于用户的仿真空闲时间，并且基于上下文推荐在业余时间执行的任务的业余时间和子任务的元数据。推荐的任务按照时间表进行管理。版权所有（C）2006，JPO＆NCIPI

8. 发明专利

JP2013069157A Natural language processing device, natural language processing method and natural language processing program 审中-公开
标题翻译：自然语言处理设备，自然语言处理方法和自然语言处理程序
公开(公告)号：JP2013069157A
公开(公告)日：2013-04-18
申请号：JP2011207823
申请日：2011-09-22
申请人： Toshiba Corp , 株式会社東芝
发明人： YAMAZAKI TOSHIHIRO , SUZUKI MASARU
IPC分类号： G06F17/27 , G06F17/30 , G06N3/00
CPC分类号： G06F17/2809
摘要： PROBLEM TO BE SOLVED: To provide a natural language processing device which generates an analyzer appropriate for a document of an analysis object, taking into consideration a language and a domain of the document.SOLUTION: A natural language processing device 100 comprises parallel translation storage means, parallel translation retrieval means, word extraction means, correct answer generation means and analyzer generation means. The parallel translation storage means stores a plurality of parallel translation documents composed of a document of an unknown language and a document of one or a plurality of known languages, and its domain. The parallel translation retrieval means designates the domain and retrieves a parallel translation document from the parallel translation storage means. The word extraction means extracts a word pair associating a word of an unknown language with a word of a known language from the parallel translation document retrieved by the parallel translation retrieval means. The correct answer generation means estimates an analysis result of the document of the unknown language in the retrieved parallel translation document using the word pair and an analysis result of the document of the known language in the retrieved parallel translation document. The analyzer generation means generates an analyzer of the unknown language using the analysis result of the document of the unknown language.
摘要翻译：要解决的问题：提供一种自然语言处理装置，其考虑到文档的语言和领域，生成适合于分析对象的文档的分析器。解决方案：自然语言处理装置100包括并行翻译存储装置，并行翻译检索装置，字提取装置，正确答案产生装置和分析器生成装置。并行翻译存储装置存储由未知语言的文档和一个或多个已知语言的文档及其域组成的多个并行翻译文档。并行翻译检索装置指定域并从并行翻译存储装置检索并行翻译文档。字提取装置从并行翻译检索装置检索的并行翻译文件中提取将未知语言的单词与已知语言的单词相关联的单词对。正确的回答生成装置使用检索的并行翻译文档中的单词对和已知语言的文档的分析结果来估计检索到的并行翻译文档中的未知语言的文档的分析结果。分析器生成装置使用未知语言的文档的分析结果生成未知语言的分析器。版权所有（C）2013，JPO＆INPIT

9. 发明专利

JP2012075044A Device, method and program for image processing 有权
标题翻译：用于图像处理的设备，方法和程序
公开(公告)号：JP2012075044A
公开(公告)日：2012-04-12
申请号：JP2010219989
申请日：2010-09-29
申请人： Toshiba Corp , 株式会社東芝
发明人： MIZUOKA YOSHIAKI , SUZUKI MASARU , HAMADA SHINICHIRO , YAMAZAKI TOSHIHIRO , YAMANAKA NORIKO
IPC分类号： H04N1/387 , G06K9/00 , G06T11/60
摘要： PROBLEM TO BE SOLVED: To provide an image processing device for processing the part in which a user is interested out of an image including characters.SOLUTION: An image processing device in an embodiment includes a capture part for capturing the image of a subject, a detection part for detecting the character region of the image, an estimation part for estimating the character recognition accuracy for the character region and a display part for superimposing and displaying incomplete region information on the image according to the character recognition accuracy of the character region.

10. 发明专利

JP2009252145A Data creating apparatus and data creating method 有权
标题翻译：数据创建设备和数据创建方法
公开(公告)号：JP2009252145A
公开(公告)日：2009-10-29
申请号：JP2008102444
申请日：2008-04-10
申请人： Toshiba Corp , 株式会社東芝
发明人： KAWAMURA TAKAHIRO , YAMAZAKI TOSHIHIRO , NAGANO SHINICHI , SHIMOGOORI YUMIKO , IIDA TAKAYUKI
IPC分类号： G06F17/30 , G06F19/00 , G06Q30/02 , G06Q30/06 , G06Q50/00
CPC分类号： G06F17/30707 , G06F17/2785 , G06F17/30722
摘要： PROBLEM TO BE SOLVED: To provide a data creating technique, capable of presenting a surprising behavior for a user, when presenting a relevant behavior related to a current behavior of the user, while ensuring security to protect the privacy.
SOLUTION: A behavioral meta data extraction part 101 extracts behavioral meta data from Web pages collected for each topic. A behavior map creation part 102 creates, for each topic, behavior map data from the behavioral meta data in reference to a behavior ontology and a commodity ontology. A behavior link weighting part 104 performs setting of a weighting factor to a link or creation of a new link in the behavior map data. A relevant behavior selection part 105 searches the behavior map data based on user information, selects a relevant behavior related to the current behavior of the user in behavior map data obtained by the search, and outputs relevant behavior information showing this behavior.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：提供数据创建技术，当呈现与用户的当前行为相关的相关行为时，能够为用户呈现出惊人的行为，同时确保保护隐私的安全性。解决方案：行为元数据提取部分101从为每个主题收集的网页中提取行为元数据。行为图创建部分102针对每个主题，针对行为本体和商品本体，从行为元数据创建行为映射数据。行为链路加权部104对行为映射数据中的链接进行加权因子的设定或创建新的链接。相关行为选择部105基于用户信息搜索行为图数据，选择与通过搜索获得的行为图数据中的用户的当前行为相关的相关行为，并输出表示此行为的相关行为信息。版权所有（C）2010，JPO＆INPIT

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式